This document describes a study that analyzed tweets and newspaper letters related to several mass school shootings to detect signs of "learned helplessness" in the public sphere. The researchers acquired Twitter data and letters to the editor related to shootings at Virginia Tech, Sandy Hook Elementary, and Umpqua Community College. They analyzed the data to compare sentiment levels and proportions of tweets/letters over time, finding that anger in responses increased after Umpqua but had previously decreased, and that the volume of tweets about shootings went down over time. The study aimed to understand shifting public dialog around mass shootings using sentiment analysis of social and traditional media sources.
Good Stuff Happens in 1:1 Meetings: Why you need them and how to do them well
SENTIMENT ANALYSIS REVEALS INCREASING ANGER AFTER UMPQUA SHOOTING
1. SENTIMENT ANALYSIS OF TWITTER DATA
& NEWSPAPER LETTERS-TO-THE-EDITOR
TO DETECT LEARNED HELPLESSNESS
IN THE PUBLIC SPHERE
Mary van Valkenburg
& Thea Ledbetter
2. Hypothesis: As a society, we have
developed learned helplessness in regard
to mass school shootings
3. “Somehow this has become routine. The
reporting is routine. My response here at
this podium ends up being routine. The
conversation in the aftermath of it. We've
become numb to this.”
President Barack Obama 10/01/2015
6. Acquire Data Wrangle
Data
Explore Data Analyze Data
The data pipeline
379 Letters
Columbine High School (91)
Amish School (18)
Virginia Tech (158)
Sandy Hook Elementary (93)
Umpqua Community College (19)
1,349,765 Tweets
Virginia Tech (1,180)
Sandy Hook Elementary (1,139,751)
Umpqua Community College (208,834)
7. Acquire Data Wrangle
Data
Explore Data Analyze Data
The data pipeline
1. Remove Retweets:
Virginia Tech (1,180 1,180)
Sandy Hook Elementary (1,139,751 597,835)
Umpqua Community College (208,834 82,000)
2. Translate Emojis (😡 “angry”)
3. Convert to lowercase (Disgusted! disgusted!)
4. Remove Stop Words (174 common words: 20 days of anguish! 20 days anguish!)
5. Remove non-alphabetic characters (20 days anguish! days anguish)
Clean
8. The data pipeline
1. Get NRC sentiment values for each tweet or letter
(Anger, Disgust, Fear, Sadness, Surprise)
2. Calculate word counts (tweets ranged from 1 to 56, letters ranged from 10 to 271 words)
3. Calculate adjusted sentiment values
2. Calculate proportion of tweets that are in response to each event by date:
2007 (Virginia Tech) – approx. 5000 tweets per day
2012 (Sandy Hook) – approx. 400,000,000 tweets per day
2015 (Umpqua) – approx. 500,000,000 tweets per day
Organize
Acquire Data Wrangle
Data
Explore Data Analyze Data
9. Sample Letter (Des Moines Register – 4/18/2007)
Our culture of violence toward people comes through in music,
books, video games, movies, the Iraq war, divorce, theft, illegal
immigration and lying on our income taxes. Then, we are
surprised when the tragedy of Virginia Tech takes place. When
we eliminate God from our lives, the animalistic behavior that lies
within each of us is allowed to come out in all its destructive fury.
Don't be surprised; it will only get worse.
word count (after processing) = 42
anger = 7, adjusted anger score = 0.1667
fear = 10, adjusted anger score = 0.2381
sadness = 9, adjusted anger score = 0.2143
disgust = 5, adjusted anger score = 0.1190
surprise = 2, adjusted anger score = 0.0476
10. Sample Tweet - 4/18/2007)
mass shooting at umpqua community college 😱
word count (after processing) = 7
anger = 3, adjusted anger score = 0.4286
fear = 3, adjusted anger score = 0.4286
sadness = 0, adjusted anger score = 0
disgust = 1, adjusted anger score = 0.1429
surprise = 0, adjusted anger score = 0
11. Acquire Data Wrangle
Data
Explore Data Analyze Data
The data pipeline
1. Create summary views:
• Message counts by date, event, source and source type
• Mean adjusted sentiment scores by event and source type
2. Create quick plots
15. Proportion of users tweeting
t.test(vt_tweets.by_date$proportion, sh_tweets.by_date$proportion, alternative = "g")
t = 2.6578, df = 27.001, p-value = 0.006526
mean of x mean of y
0.0084285714 0.0000515375
t.test(ucc_tweets.by_date$proportion, sh_tweets.by_date$proportion, alternative = "l")
t = -4.0666, df = 31.246, p-value = 0.0001501
mean of x mean of y
5.655172e-06 5.153750e-05
19. t-test for significance in increased anger after Umpqua
as compared to anger after Sandy Hook
t.test(Umpqua.anger, SandyHook.anger, alternative = "g")
Welch Two Sample t-test
data: Umpqua.anger and SandyHook.anger
t = 93.156, df = 101120, p-value < 2.2e-16
alternative hypothesis: true difference in means is greater than 0
95 percent confidence interval: 0.02285762 Inf
sample estimates:
mean of x mean of y
0.06516975 0.04190128
20. • Oregon college shooting: Shock, fear and confusion after attack at
Umpqua Community College
• Another gun massacre in the States
• senseless. https://t.co/22WtC4Jfll
• holy hell the #Umpqua shooting...
• Horrible. https://t.co/I30SEODIUB
• Damn crazy at Umpqua .been there before when I stayed up there.
• Heard about umpqua college shooting attack. Crazy !
• im so in shock because of the umpqua shooting i do not even have words
21. Acquire Data Wrangle
Data
Explore Data
The data pipeline
Analyze Data
Is there a difference in the sentiment content of letters vs tweets?
22. t = 9.1543, p-value < 2.2e-16 t = 8.7403, p-value < 2.2e-16 t = 10.972, p-value < 2.2e-16
t = 9.6111, p-value < 2.2e-16 t = 9.2149, p-value < 2.2e-16
23. Concluding Thoughts
• Letters show more intense sentiment than tweets, even after controlling for
differences in word counts.
• Anger in response to mass school shootings appears to have trended
downward through the first four mass shootings studied. However, anger
rose significantly with the last event, the shooting at Umpqua Community
College.
• The proportion of tweets that were about mass school shootings declined
from Virginia Tech in 2007 to Sandy Hook in 2012. They continued to
decrease with the Umpqua Community College shooting in 2015.
24. “Sentiment analysis is a very specific tool
that's useful in certain situations,
but it isn't magic.”
-David Robinson
(quoted in Scientific American 8/18/2016)
Editor's Notes
We wanted to look at how Americans react to mass school shootings. It seems like complacency -- a kind of resignation -- has settled in. If we have -- as a society -- largely given up on being able to slow or stop school shootings, this would mean that we – as a society are in a state of learned helplessness regarding these events. Our plan for testing this hypothesis involves mining what everyday people are saying in response to school shootings to understand how sentiment has changed. We would expect to see a muting of sentiment or even a disappearance of conversation about school shootings if out hypothesis is true.
Here’s a quote from a speech by President Obama following last year’s shooting at Umpqua Community College in Oregon.
Where do people go to talk about things like school shootings? There’s an idea that has been elaborated extensively by German philosopher Jurgen Habermas. The notion of the Public Sphere. The public sphere is a place -- physical or virtual -- where people can come together to engage in critical public debate. Twitter is one of today’s most active and accessible public spheres. Newspaper letters to the editor represent another public sphere.
Our plan was to mine tweets and letters related to school shootings in the 30 days following each event to try to understand how sentiment has changed.
People who hang out in the Twitter sphere aren’t always the same as those who participate in the letters sphere. Because of that we decided to track and analyze these two sources separately. Maybe one group is more prone to learned helplessness…we wanted to find out.